keras-team/keras · error · TypeError

Invalid input type. Expected `float32` or `float64`. Receive

Error message

Invalid input type. Expected `float32` or `float64`. Received: input type={x.dtype}

What it means

Error "Invalid input type. Expected `float32` or `float64`. Received: input type={x.dtype}" thrown in keras-team/keras.

Source

Thrown at keras/src/backend/tensorflow/math.py:181

def rfft(x, fft_length=None):
    if fft_length is not None:
        fft_length = [fft_length]
    complex_output = tf.signal.rfft(x, fft_length=fft_length)
    return tf.math.real(complex_output), tf.math.imag(complex_output)


def irfft(x, fft_length=None):
    complex_input = _get_complex_tensor_from_tuple(x)
    if fft_length is not None:
        fft_length = [fft_length]
    return tf.signal.irfft(complex_input, fft_length)


def stft(
    x, sequence_length, sequence_stride, fft_length, window="hann", center=True
):
    if standardize_dtype(x.dtype) not in {"float32", "float64"}:
        raise TypeError(
            "Invalid input type. Expected `float32` or `float64`. "
            f"Received: input type={x.dtype}"
        )
    if fft_length < sequence_length:
        raise ValueError(
            "`fft_length` must equal or larger than `sequence_length`. "
            f"Received: sequence_length={sequence_length}, "
            f"fft_length={fft_length}"
        )
    if isinstance(window, str):
        if window not in {"hann", "hamming"}:
            raise ValueError(
                "If a string is passed to `window`, it must be one of "
                f'`"hann"`, `"hamming"`. Received: window={window}'
            )
    x = convert_to_tensor(x)

    if center:

View on GitHub (pinned to 7a34a03db6)

When it happens

Trigger: Thrown at keras/src/backend/tensorflow/math.py:181 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of keras-team/keras@7a34a03db6 (2026-08-25). Data as JSON: /api/errors/1babb3e83077100b. Report an issue: GitHub.